AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

High-Level Semantic Feature Matters Few-Shot Unsupervised Domain Adaptation

Lei Yu, Wanqi Yang, Shengqi Huang, Lei Wang, Ming Yang

AAAI 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace local features with task-specific semantic featuresIMSE · DomainNet 5-way 1-shot, averageaccuracy: 48.86 -> 52.79Improved
Add cross-domain self-training to task-specific semantic embedding (ablation)TSE · DomainNet, sketch → clipart, real, quickdraw, paintingaccuracy: 61.98 -> 68.25; 60.00 -> 61.15; 52.21 -> 58.31; 51.62 -> 53.34Improved
Add cross-attention to task-specific semantic embedding (ablation)TSE · DomainNet, sketch → clipart, real, quickdraw, paintingaccuracy: 61.98 -> 62.74; 60.00 -> 60.54; 52.21 -> 53.64; 51.62 -> 54.23Improved
Add task-specific semantic embedding to cross-domain self-training (ablation)Cross-domain self-training · DomainNet, sketch → clipart, real, quickdraw, paintingaccuracy: 57.07 -> 68.25; 53.31 -> 61.15; 41.93 -> 58.31; 46.66 -> 53.34Improved
Add cross-attention and cross-domain self-training to TSE (ablation)TSE · DomainNet, sketch → clipart, real, quickdraw, paintingaccuracy: 68.25 -> 69.45; 61.15 -> 65.00; 58.31 -> 62.25; 53.34 -> 56.51Improved
Add semantic feature alignment loss (ablation)TSECS · DomainNet, sketch → clipart, real, quickdraw, paintingaccuracy: 66.83 -> 68.04; 58.29 -> 63.98; 56.51 -> 59.13; 44.25 -> 55.39Improved
Add class matching loss (ablation)TSECS · DomainNet, sketch → clipart, real, quickdraw, paintingaccuracy: 66.67 -> 68.04; 58.84 -> 63.98; 56.91 -> 59.13; 43.28 -> 55.39Improved
Add similarity pattern alignment loss to semantic feature alignment and class matching (ablation)TSECS · DomainNet, sketch → clipart, real, quickdraw, paintingaccuracy: 68.04 -> 69.45; 63.98 -> 65.00; 59.13 -> 62.25; 55.39 -> 56.51Improved
Add all three domain alignment and class matching losses (ablation)TSECS · DomainNet, sketch → clipart, real, quickdraw, paintingaccuracy: 66.67 -> 69.45; 58.84 -> 65.00; 56.91 -> 62.25; 43.28 -> 56.51Improved
Use cross-domain self-training without semantic embedding (ablation)TSECS · DomainNet, sketch → clipartaccuracy: 69.45 -> 57.07Hurt
Train on DomainNet and evaluate on miniImageNetTSECS · miniImageNet 5-way 1-shot, real → sketchaccuracy: 48.52±0.81 -> 49.83±0.96Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy